Publications (17)
LingDT-VL-OCR: Structure-Aware Document-Level Parsing with Fine-Grained Visual Reference
Siyi Qian, Xiongfei Bai, Bingtao Fu +4
In this paper, we propose LingDT-VL-OCR, a document parsing system tailored to financial-domain documents, transforming ultra-long financial PDFs into semantically consistent, high…
High-rate quantum key distribution exceeding 110 Mb/s
Wei Li, Likang Zhang, Hao Tan +14
Quantum key distribution (QKD) can provide fundamentally proven security for secure communication. Toward application, the secret key rate (SKR) is a key figure of merit for any QK…
Analysis of lane-change conflict between cars and trucks at merging section using UAV video data
Yichen Lu, Kai Cheng, Yue Zhang +2
The freeway on-ramp merging section is often identified as a crash-prone spot due to the high frequency of traffic conflicts. Very few traffic conflict analysis studies comprehensi…
Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
Jiatong Shi, Jionghao Han, Yichen Lu +6
Role-play has become a key testbed for generative models, expanding from text-only dialogue to multimodal interaction. Extending role-play to speech captures prosody, emotion, and…
FastAdaSP: Multitask-Adapted Efficient Inference for Large Speech Language Model
Yichen Lu, Jiaqi Song, Chao-Han Huck Yang +1
In this study, we aim to explore Multitask Speech Language Model (SpeechLM) efficient inference via token reduction. Unlike other modalities such as vision or text, speech has uniq…
Tracing Copied Pixels and Regularizing Patch Affinity in Copy Detection
Yichen Lu, Siwei Nie, Minlong Lu +3
Image Copy Detection (ICD) aims to identify manipulated content between image pairs through robust feature representation learning. While self-supervised learning (SSL) has advance…
ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning
Yichen Lu, Wei Dai, Jiaen Liu +9
LLM-based translation agents have achieved highly human-like translation results and are capable of handling longer and more complex contexts with greater efficiency. However, they…
Twin-field quantum key distribution without phase locking
Wei Li, Likang Zhang, Yichen Lu +11
Twin-field quantum key distribution (TF-QKD) has emerged as a promising solution for practical quantum communication over long-haul fiber. However, previous demonstrations on TF-QK…
Swarming Lattice in Frustrated Vicsek-Kuramoto Systems
Yichen Lu, Yingshan Guo, Yiyi Zhang +2
We introduce a frustration parameter into the Vicsek-Kuramoto systems of self-propelled particles. While the system exhibits conventional synchronized states, such as global p…
Avatar Knowledge Distillation: Self-ensemble Teacher Paradigm with Uncertainty
Yuan Zhang, Weihua Chen, Yichen Lu +3
Knowledge distillation is an effective paradigm for boosting the performance of pocket-size model, especially when multiple teacher models are available, the student would break th…
Dive into the Resolution Augmentations and Metrics in Low Resolution Face Recognition: A Plain yet Effective New Baseline
Xu Ling, Yichen Lu, Wenqi Xu +5
Although deep learning has significantly improved Face Recognition (FR), dramatic performance deterioration may occur when processing Low Resolution (LR) faces. To alleviate this,…
SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation via Language Model and Synthetic Data
Yichen Lu, Jiaqi Song, Xuankai Chang +3
In this work, we present SynesLM, an unified model which can perform three multimodal language understanding tasks: audio-visual automatic speech recognition(AV-ASR) and visual-aid…
Noisy Positive-Unlabeled Learning with Self-Training for Speculative Knowledge Graph Reasoning
Ruijie Wang, Baoyu Li, Yichen Lu +6
This paper studies speculative reasoning task on real-world knowledge graphs (KG) that contain both \textit{false negative issue} (i.e., potential true facts being excluded) and \t…
Enhancing Audiovisual Speech Recognition through Bifocal Preference Optimization
Yihan Wu, Yichen Lu, Yifan Peng +3
Audiovisual Automatic Speech Recognition (AV-ASR) aims to improve speech recognition accuracy by leveraging visual signals. It is particularly challenging in unconstrained real-wor…
Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study
Xuankai Chang, Brian Yan, Kwanghee Choi +14
Speech signals, typically sampled at rates in the tens of thousands per second, contain redundancies, evoking inefficiencies in sequence modeling. High-dimensional speech features…
Robust Audiovisual Speech Recognition Models with Mixture-of-Experts
Yihan Wu, Yifan Peng, Yichen Lu +3
Visual signals can enhance audiovisual speech recognition accuracy by providing additional contextual information. Given the complexity of visual signals, an audiovisual speech rec…
The Future will be Different than Today: Model Evaluation Considerations when Developing Translational Clinical Biomarker
Yichen Lu, Jane Fridlyand, Tiffany Tang +3
Finding translational biomarkers stands center stage of the future of personalized medicine in healthcare. We observed notable challenges in identifying robust biomarkers as some w…